© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50343
    Prev
    Next
    INDEX
    Explanations

    busy periods and activities

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is detecting occurrences of the word “busy” (including its inflected forms like “busier”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     présenter
    -1.05
    Journey
    -0.98
     ロ
    -0.95
     to
    -0.94
     apresent
    -0.91
     stopping
    -0.90
     त्र
    -0.90
     ekos
    -0.90
     voyage
    -0.89
    sira
    -0.89
    POSITIVE LOGITS
     busy
    1.95
    busy
    1.80
     Busy
    1.77
    Busy
    1.37
     schedule
    1.35
    BUSY
    1.30
     busiest
    1.23
     bees
    1.17
     Bees
    1.16
     schedules
    1.16
    Activations Density 0.012%

    No Known Activations